Question Answering by Reasoning Across Documents with Graph Convolutional Networks
This addresses the challenge of answering questions that require information from multiple documents, which is incremental as it builds on existing reading comprehension methods.
The paper tackles the problem of multi-document question answering by integrating and reasoning across documents using a graph-based neural model, achieving state-of-the-art results on the WikiHop dataset.
Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference). Graph convolutional networks (GCNs) are applied to these graphs and trained to perform multi-step reasoning. Our Entity-GCN method is scalable and compact, and it achieves state-of-the-art results on a multi-document question answering dataset, WikiHop (Welbl et al., 2018).